Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Teknokes

AI-Powered Holter for Affordable and Accurate Arrhythmia Detection Nyatte, Steyve; Leatitia, Guiadem; steve, Perabi; Essiane, Ndjakomo
Jurnal Teknokes Vol. 18 No. 2 (2025): June
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Cardiac arrhythmias pose significant health risks, and current detection systems often suffer from high costs and limited accessibility, particularly in resource-constrained settings. This research aimed to develop a portable, cost-effective Holter monitoring device for accurate arrhythmia detection using machine learning. By combining an inexpensive ESP32 microcontroller with an AD8232 ECG sensor, a data acquisition system was built. Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Multilayer Perceptron (MLP) models were trained and evaluated for arrhythmia classification. The SVM model achieved the highest accuracy (78.53%) using a linear kernel and features selected by a random forest algorithm. While KNN and MLP also showed promise, the results emphasized the importance of hyperparameter tuning and feature selection. This research demonstrated the feasibility of creating an affordable and intelligent Holter device capable of effective arrhythmia detection, potentially increasing access to cardiac monitoring and enabling early diagnosis in resource-limited environments.
Comparison of Pressure Sensor in Flow Analyzer Design for Peep Measurement on Ventilators Wakidi, Levana Forra; Amrinsani, Farid; Zeha, Alfi Nur; Dewiningrum, Riqqah; Nyatte, Steyve
Jurnal Teknokes Vol. 16 No. 4 (2023): December
Publisher : Jurusan Teknik Elektromedik, Politeknik Kesehatan Kemenkes Surabaya, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Flow Analyzer allows measurement of flow, pressure, volume, and oxygen concentration delivered to the patient, with PEEP (Positive End Expiratory Pressure) being a crucial parameter in mechanical ventilation. Incorrect PEEP values can elevate the risk of patient mortality. The recommended PEEP range is 5-24 cmH2O, and administration is determined by the patient's clinical condition. This research aims to identify stable and highly accurate pressure sensors by comparing the MPX2010DP and MPX5010DP sensors with pressure readings from a Digital Pressure Meter (DPM). The study involves 5 repetitions of a lung test, each with 11 pressure reading points, within a pressure measurement range of 0-30 cmH2O. The DPM has a resolution of 1 cmH2O, while both pressure sensors have a resolution of 0.01 cmH2O. Results indicated that the MPX2010DP sensor has the smallest error percentage, specifically 0.00%, at a pressure increase of 5 cmH2O and 20 cmH2O. Conversely, the MPX2010DP sensor shows the largest error percentage, 5.16%, when the pressure decreases by 5 cmH2O. The highest standard deviation of 0.52 is observed in the MPX5010DP sensor at a 20 cmH2O pressure increase, while the maximum correction value of 0.54 is found in the MPX5010DP sensor at a 25 cmH2O pressure increase. According to the ANOVA test, there is no significant difference in pressure produced between the MPX2010DP sensor, MPX5010DP sensor, and DPM. The sensors are well-calibrated and provide accurate readings according to calibration tool standards. Therefore, the MPX2010DP and MPX5010DP sensors are deemed accurate for measuring PEEP parameters in ventilators. Based on the obtained data, it can be concluded that the MPX2010DP sensor is more accurate and stable.